A Snapshot-based Approach for Self-supervised Feature Learning and Weakly-supervised Classification on Point Cloud Data

Xingye Li, Zhigang Zhu, Zhigang Zhu

Abstract

Manually annotating complex scene point cloud datasets is both costly and error-prone. To reduce the reliance on labeled data, we propose a snapshot-based self-supervised method to enable direct feature learning on the unlabeled point cloud of a complex 3D scene. A snapshot is defined as a collection of points sampled from the point cloud scene. It could be a real view of a local 3D scan directly captured from the real scene, or a virtual view of such from a large 3D point cloud dataset. First the snapshots go through a self-supervised pipeline including both part contrasting and snapshot clustering for feature learning. Then a weakly-supervised approach is implemented by training a standard SVM classifier on the learned features with a small fraction of labeled data. We evaluate the weakly-supervised approach for point cloud classification by using varying numbers of labeled data and study the minimal numbers of labeled data for a successful classification. Experiments are conducted on three public point cloud datasets, and the results have shown that our method is capable of learning effective features from the complex scene data without any labels.

Download


Paper Citation


in Harvard Style

Li X. and Zhu Z. (2021). A Snapshot-based Approach for Self-supervised Feature Learning and Weakly-supervised Classification on Point Cloud Data.In Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, ISBN 978-989-758-488-6, pages 399-408. DOI: 10.5220/0010230103990408


in Bibtex Style

@conference{visapp21,
author={Xingye Li and Zhigang Zhu},
title={A Snapshot-based Approach for Self-supervised Feature Learning and Weakly-supervised Classification on Point Cloud Data},
booktitle={Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP,},
year={2021},
pages={399-408},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010230103990408},
isbn={978-989-758-488-6},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP,
TI - A Snapshot-based Approach for Self-supervised Feature Learning and Weakly-supervised Classification on Point Cloud Data
SN - 978-989-758-488-6
AU - Li X.
AU - Zhu Z.
PY - 2021
SP - 399
EP - 408
DO - 10.5220/0010230103990408